Abstract
The National Children's Study (NCS) statistics and item response theory group was tasked with promoting the quality of study measures and analysis. This paper provides an overview of six measurement and statistical considerations for the NCS: (1) Conceptual and Measurement Model; (2) Reliability; (3) Validity; (4) Measurement Invariance; (5) Interpretability of Scores; and (6) Burden of administration. The guidance was based primarily on recommendations of the International Society of Quality of Life Research.
Highlights
The National Children’s Study (NCS) was an “integrated systems-based initiative to assess a full spectrum of health and capture the environmental factors and other influences that shape the trajectory of child development” [1]
The Statistics and Item Response Theory Group facilitated the quality of measures developed for the NCS and worked to ensure adherence to high standards of measurement (Tables 1, 2)
We developed a measurement template as a fillable form for Domain team members to provide information on the name of proposed measure, a summary description of the measure, the type of data collection for the measure, the measurement target, the respondent, the exposure or outcome measure, the age band of the measurement target, the mode of administration, the location of administration, the estimated time to administer, how the measure is scored, evidence for reliability and validity, whether the measure is an existing measure and if there are fees associated with use, an adaptation of an existing measure or a new measure, and special conditions for administration
Summary
The National Children’s Study (NCS) was an “integrated systems-based initiative to assess a full spectrum of health and capture the environmental factors and other influences that shape the trajectory of child development” [1]. The Statistics and Item Response Theory Group facilitated the quality of measures developed for the NCS and worked to ensure adherence to high standards of measurement (Tables 1, 2). Conceptual and measurement model – The conceptual model provides a description and framework for the targeted construct(s) to be included in a Participant Reported Outcome (PRO) measure. Construct validity – The degree to which scores on the PRO measure relate to other measures (e.g., participant- or patient-reported or clinical indicators) in a manner that is consistent with theoretically derived a priori hypotheses concerning the concepts that are being measured. Measures are only valid if the participants in a study can understand what is being asked of them and can provide a response that accurately reflects their experiences, perspectives, abilities and/or levels of development. The key aspects of measures are: [1] Conceptual Framework and Measurement Model; [2] Reliability; [3] Validity; [4] Measurement Invariance; [5] Interpretability of Scores; and [6] Burden of administration
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
